开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)|3.2.5(安卓)APP下载

RyanR · 2023年10月24日

参数法和非参数法的选择

NO.PZ2018122701000002

问题如下:

A risk analyst is comparing the use of parametric and non-parametric approaches for calculating VaR and is concerned about some of the characteristics present in the loss data. Which of the following distribution characteristics would make parametric approaches the favored method to use?

选项:

A.

Skewness in the distribution

B.

Fat tails in the distribution

C.

Scarcity of high magnitude loss events

D.

Heteroskedasticity in the distribution

解释:

C is correct.

考点 non-parametric method

解析 Non-parametric approaches can accommodate fat tails, skewness, and any other non-normal features that can cause problems for parametric approaches. However, if the data period that is used in estimation includes few losses or losses with low magnitude, non-parametric methods will often produce risk measures that are too low. Hence parametric methods would be more appropriate in those situations.

这个知识点掌握的不是很牢固,这道题还理解的不太透彻,想跟老师再学习一下:

参数法就是normal和lognormal两种,

AB:lognormal也是有偏或者肥尾啊?

C:选项是因为极端值少,所以用非参数法的优势就不大,但是如果参数法会不会更可能不合适啊?

D:异方差就导致不能很好估计参数,所以不能选。


谢谢老师

1 个答案

DD仔_品职助教 · 2023年10月26日

嗨,爱思考的PZer你好:


同学你好,

AB即使分布有肥尾和偏度,也没有办法像非参数法那样很好的代表数据。

C极端值少说明不是极值分布,那么用正常的分布比非参数法更好。

D对的

----------------------------------------------
加油吧,让我们一起遇见更好的自己!

  • 1

    回答
  • 0

    关注
  • 243

    浏览
相关问题

NO.PZ2018122701000002 问题如下 A risk analyst is comparing the use of parametric annon-parametric approaches for calculating Vanis concerneabout some of the characteristipresent in the loss tWhiof the following stribution characteristiwoulmake parametric approaches the favored methoto use? Skewness in the stribution Ftails in the stribution Scarcity of high magnitu loss events Heteroskesticity in the stribution C is correct. 考点 : non-parametric method 解析 : Non-parametric approaches caccommote fat tails, skewness, anany other non-normfeatures thccause problems for parametric approaches. However, if the ta periothis usein estimation inclus few losses or losses with low magnitu, non-parametric metho will often prorisk measures thare too low. Henparametric metho woulbe more appropriate in those situations. 忘记这个知识点了

2023-03-26 05:44 1 · 回答

NO.PZ2018122701000002 Ftails in the stribution Scarcity of high magnitu loss events Heteroskesticity in the stribution C is correct. 考点 non-parametric metho解析 Non-parametric approaches caccommote ftails, skewness, anany other non-normfeatures thccause problems for parametric approaches. However, if the ta periothis usein estimation inclus few losses or losses with low magnitu, non-parametric metho will often prorisk measures thare too low. Henparametric metho woulmore appropriate in those situations. 尤其是后面however那段

2022-09-29 19:34 2 · 回答

NO.PZ2018122701000002

2021-04-08 00:40 1 · 回答

问一道题:NO.PZ2018122701000002

2020-12-21 17:17 2 · 回答